Machine learning-based obesity classification considering 3D body scanner measurements

Abstract

Obesity can cause various diseases and is a serious health concern. BMI, which is currently the popular measure for judging obesity, does not accurately classify obesity; it reflects the height and weight but ignores the characteristics of an individual’s body type. In order to overcome the limitations of classifying obesity using BMI, we considered 3-dimensional (3D) measurements of the human body. The scope of our study was limited to Korean subjects. In order to expand 3D body scan data clinically, 3D body scans, Dual-energy X-ray absorptiometry, and Bioelectrical Impedance Analysis data was collected pairwise for 160 Korean subjects. A machine learning-based obesity classification framework using 3D body scan data was designed, validated through Accuracy, Recall, Precision, and F1 score, and compared with BMI and BIA. In a test dataset of 40 people, BMI had the following values: Accuracy: 0.529, Recall: 0.472, Precision: 0.458, and F1 score: 0.462, while BIA had the following values: Accuracy: 0.752, Recall: 0.742, Precision: 0.751, and F1 score: 0.739. Our proposed model had the following values: Accuracy: 0.800, Recall: 0.767, Precision: 0.842, and F1 score: 0.792. Thus, our accuracy was higher than BMI as well as BIA. Our model can be used for obesity management through 3D body scans.

Predicting Obesity in Nutritional Patients using Decision Tree Modeling

“…After evaluating several studies related to the topic presented in this research, we refer to the results found in the studies most like this work, which aim to predict obesity. For example, a study [40] predicted obesity using 3D scanner data with an accuracy of 80% and an accuracy of 84%, which are lower than the results obtained in this work. However, in the study [23], which predicted the risk of childhood obesity using a dataset of 18,818 infants in four age periods and applying seven ML algorithms, the Multilayer Perceptron algorithm obtained the best indicator with an accuracy of 96%, which is higher than the results of this work.…”

“…In addition, students, researchers, and independent groups have published papers that aim to address the problem of obesity using technology. For example, in study [22], a study analyzed six ML techniques to create a model capable of classifying obesity in individuals using a 3D scanner, X-ray equipment, and a body composition analyzer. The study obtained indicators above 75%, with the Random Forest technique presenting the best results.…”

AI Somatotype System Using 3D Body Images: Based on Deep-Learning and Transfer Learning

“…Moreover, data in the form of various body measurements including height, circumference, cross-sectional area, and volume are collected [10]. Previous studies have shown that the use of machine learning algorithms to predict obesity based on body fat percentage [11] outperforms BMI (Body Mass Index) and BIA (Bioelectrical Impedance Analysis) in the classification of obesity. In addition, research exploring predictive models for somatotypes based on anthropometry [12] has shown excellent performance in classifying body types.…”

Chronic Diseases: A Comprehensive Review of Applications for Prediction of Obesity

“…

Recent advancements in ML have opened new avenues for addressing complex health issues by facilitating personalized medicine, predictive diagnostics, and behaviour modification strategies. In the context of obesity, ML algorithms can analyse vast datasets-from genetic predispositions to behavioural and environmental factors-enabling the development of tailored intervention strategies that are more adaptive and responsive to individual needs [9,10]. Moreover, ML can enhance the real-time monitoring and management of obesity through wearable technology and mobile applications, offering immediate feedback and support to individuals as they navigate their daily choices [11,12].

…”